Seeing What Few-Shot Learners See: Contrastive Cross-Class Attribution for Explainability

Few-shot learning (FSL) enables deep learning models to generalize to unseen categories with minimal labeled data, making it crucial for data-constrained domains such as healthcare. However, existing FSL models often lack explainability, obscuring the reasoning behind their predictions and limiting trust in their deployment. In this work, we introduce contrastive cross-class attribution (C3A) to enhance explainability in FSL. Specifically, we present C3A for explaining query predictions and its